Author name: Oh Hyun-Bin, Yuhta Takida, Toshimitsu Uesaka, Tae-Hyun Oh, Yuki Mitsufuji

arXiv:2512.08282v2 Announce Type: replace
Abstract: Recent advances in Video-to-Audio (V2A) generation have achieved impressive perceptual quality and temporal synchronization, yet most models remain appearance-driven, capturing visual-acoustic correl…